R Notebook

library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(countrycode)
df <- read_csv("survey_results_public.csv")

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   .default = col_character(),
##   Respondent = col_double(),
##   Age = col_double(),
##   CompTotal = col_double(),
##   ConvertedComp = col_double(),
##   WorkWeekHrs = col_double()
## )
## ℹ Use `spec()` for the full column specifications.

DFF <- select(df, MainBranch, Country,Gender,Age, YearsCode, YearsCodePro ,EdLevel,Employment, JobSat, OrgSize, WorkWeekHrs, NEWOvertime, NEWOnboardGood, JobSeek, NEWLearn, LanguageWorkedWith,PlatformWorkedWith)
DF_USA <- DFF[DFF$Country == "United States" & !is.na(DFF$Country) & DFF$MainBranch == "I am a developer by profession" & !is.na(DFF$MainBranch), ][3:17]
DF_LC <- cbind(region = as.character(countrycode(sourcevar = DFF$Country,
                            origin = "country.name",
                            destination = "region")), DFF)

## Warning in countrycode(sourcevar = DFF$Country, origin = "country.name", : Some values were not matched unambiguously: Nomadic

DF_LC <- DF_LC[DF_LC$region == "Latin America & Caribbean" & !is.na(DF_LC$region) & DFF$MainBranch == "I am a developer by profession" & !is.na(DFF$MainBranch), ][, 4:18]
DF_MIX <- cbind(region = as.character(countrycode(sourcevar = DFF$Country,
                            origin = "country.name",
                            destination = "region")), DFF)

## Warning in countrycode(sourcevar = DFF$Country, origin = "country.name", : Some values were not matched unambiguously: Nomadic

DF_MIX <- DF_MIX[((DF_MIX$region == "Latin America & Caribbean" & !is.na(DF_MIX$region)) | (DF_MIX$Country == "United States" & !is.na(DF_MIX$Country))) &  DF_MIX$MainBranch == "I am a developer by profession" & !is.na(DF_MIX$MainBranch), ][, 3:18]
DF_MIX$Country[DF_MIX$Country != "United States"] <- "SA"
DF_MIX$Country[DF_MIX$Country == "United States"] <- "USA"
colnames(DF_MIX)[which(names(DF_MIX) == "Country")] <- "Region"
DF_MIX

Tabla Descriptores

Pregunta	Variable	Tipo de Variable
Which of the following describe you, if any? Please check all that apply. If you prefer not to answer, you may leave this question blank.	Genero	Nominal
What is your age (in years)? If you prefer not to answer, you may leave this question blank.	Edad	Discreta
Including any education, how many years have you been coding in total?	Años codeando	Discreta

Análisis de variables

Genero

#(strsplit(DF_USA$Gender, ";"))

#pie(DF_USA$Gender, na.rm = T)

Edad

boxplot(DF_MIX$Age~DF_MIX$Region, na.rm= T, xlab = "Region", ylab = "Edad")
abline(h=mean(DF_USA$Age, na.rm = TRUE), col = "red")
abline(h=mean(DF_LC$Age, na.rm = TRUE), col = "blue")

Podemos observar que blablablabla

Años Codeado

boxplot(as.numeric(DF_MIX$YearsCode)~DF_MIX$Region, na.rm= T, xlab = "Region", ylab = "Años Codeando")

## Warning in eval(predvars, data, env): NAs introduced by coercion

abline(h=mean(as.numeric(DF_USA$YearsCode), na.rm = TRUE), col = "red")

## Warning in mean(as.numeric(DF_USA$YearsCode), na.rm = TRUE): NAs introduced by
## coercion

abline(h=mean(as.numeric(DF_LC$YearsCode), na.rm = TRUE), col = "blue")

## Warning in mean(as.numeric(DF_LC$YearsCode), na.rm = TRUE): NAs introduced by
## coercion

### Años codeado profesionalmente ### Grado educativo ### Tipo de empleo ### Satisfacción con empleo ### Tamaño de organizacion en la que trabaja ### Horas trabajadas semanalmente ### Frecuencia de horas extra en el trabajo